Skip to main navigation Skip to search Skip to main content

Multi-stage moving object recognition based on fuzzy integral

  • Li Wang*
  • , Hai Hong Wang
  • , Xiao Peng Ji
  • *Corresponding author for this work
  • Ocean University of China

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A multi-stage objects recognition process based on biomimetic pattern recognition (BPR) and Chaquet integral (CI) is proposed to detect and classify the moving objects in video sequence in the intersections. It is difficult to distinguish motorcycle from pedestrians when occlusions happen. In order to solve the problem, BPR is first used to classify the Zernike moments extracted, and Cl is then adopted for multi-features fusion based on the output of BPR, the area and the velocity to improve the accuracy. An Experimental example is proposed to test the efficiency of the approach presented.

Original languageEnglish
Title of host publicationProceedings - Third International Conference on Natural Computation, ICNC 2007
PublisherIEEE Computer Society
Pages676-680
Number of pages5
ISBN (Print)0769528759, 9780769528755
DOIs
StatePublished - 2007
Event3rd International Conference on Natural Computation, ICNC 2007 - Haikou, Hainan, China
Duration: 24 Aug 200727 Aug 2007

Publication series

NameProceedings - Third International Conference on Natural Computation, ICNC 2007
Volume2

Conference

Conference3rd International Conference on Natural Computation, ICNC 2007
Country/TerritoryChina
CityHaikou, Hainan
Period24/08/0727/08/07

Fingerprint

Dive into the research topics of 'Multi-stage moving object recognition based on fuzzy integral'. Together they form a unique fingerprint.

Cite this